Key issues in the quality assurance of the One Number Census

As part of the 2001 Census, the One Number Census project estimated and adjusted the Census database for underenumeration. As a result of the highly innovative One Number Census and the Quality Assurance process it encompassed, it was also ensured that robust results could be obtained for each local authority area. This article examines some of the issues and analyses that were undertaken as part of that assessment of the 2001 Census population counts for England and Wales. The article firstly highlights the key issues surrounding the implementation of the 2001 Census fieldwork. The article then explores the 2001 Census results through a series of demographic analyses to illustrate the sorts of issues investigated during the One Number Census Quality Assurance process itself. These analyses look at the patterns contained within the results, and comparisons with key alternative sources of population counts. Overall, these in-depth analyses and investigations provide further credence to the plausibility of the One Number Census results.     

Population estimates; backseries methodology for 1992-2000

In each decade, population estimates are rebased using data from the most recent census. However, this would lead to a step change in the population estimates series. To avoid this discontinuity the backseries for 1992 to 2000, was revised to bring it into line with the 2001 Census. This article discusses the methodology used to produce the final revised backseries for 1992 to 2000 published by ONS in October 2004. The final estimates were produced after a long period of research into the best methodology to use. Traditionally, the backseries have been revised using an interim simple period method, followed by a final simple cohort method. The approach taken following the 2001 Census was much more comprehensive. This article outlines this approach, summarises the range of methods available and describes in detail the final method selected.     

Population bases and the 2011 Census

In an increasingly complex society there are a number of different population definitions that can be relevant for users, beyond the standard definition used in counting the population. This article describes the enumeration base for the 2011 Census and how alternative population outputs may be produced. It provides a background as to how the questions on the questionnaire were decided upon and how population bases can be constructed from the Census. Similarities and differences between the information collected across the three UK Censuses (England and Wales, Scotland and Northern Ireland) are discussed. Finally, issues around estimating the population on alternative bases are presented.     

2011 census coverage assessment and adjustment strategy

Every effort is made to ensure everyone is counted in a census. However, no census is perfect and some people are missed. This underenumeration does not usually occur uniformly across all geographical areas or across other sub-groups of the population such as age and sex groups. Coverage levels in censuses across the world are declining leading to an increasing need to firstly slow the decline through improved enumeration, and secondly in improved methods and data for measuring coverage. In order to achieve the mission critical aims of the 2011 Census, a coverage assessment and adjustment strategy is required. This article outlines the proposed strategy for the 2011 UK Census. The strategy is to significantly improve upon the 2001 One Number Census, and use it as a platform to develop an improved coverage assessment and adjustment methodology. The article also outlines the key areas of innovation for the 2011 strategy and the options that will be considered in order to develop the final strategy. Stakeholder management is also an important part of the strategy to ensure that key users both buy into and understand the methodology. ONS will look to build on the consultation carried out prior to the 2001 Census and widen the user base with which it engages on this important topic.     

2011 Census Field design: getting the numbers right

A labour force of over 30,000 temporary field staff has been employed to carry out the Census. This article summarises the role of the field staff in collecting census questionnaires from households and communal establishments for the March 2011 enumeration. Building on the lessons learned from the 2001 Census, and taking account of changes in society and technology since 2001, the article provides a summary of the planned field staff structures and processes intended to deal with returned questionnaires and non-responders.     

The 2011 Census: a proposed design for England and Wales

This article sets out the proposed design for a 2011 Census in England and Wales, as part of the ONS's proposed future population statistics system. The design draws on experiences from the 2001 Census and changes in available technology, and takes account of the many comments received from respondents to a Discussion Paper published in October 2003 and of views expressed at a joint ONS/RSS Conference on 11-12 November 2003. The article highlights the statistical and operational strategic aims for the 2011 Census, the major changes proposed from the 2001 approach, and gives an indication of the benefits and risks. It is important to note that this design remains a proposal at present, the elements of which will be subject to further research building on comments received during consultation and a detailed testing programme over the coming years.     

Rebasing the annual mid-year population estimates for England and Wales

The ONS produces mid-year population estimates annually, which are based on updating from the most recent census. Therefore, whenever results become available from a census, a new base is created for the population estimates. This has implications for historic series, which need to be revised to be consistent with both the past and the most recent census. This article describes the methodology that will be used for this rebasing of the mid-year population estimates following the availability of results from the 2001 Census. Census results also provide a unique opportunity to assess the accuracy of the population estimates that are based on the previous census and this article also describes the approach that will be taken to the assessment of accuracy.     

Population bases and statistical provision: towards a more flexible future?

In an increasingly complex and mobile society, there is a need for population estimates to be produced on a more flexible basis. Different uses of population data may require information to be output on different population bases, such as where people usually live ('usual residence') or where they are on a particular day ('population present'). This article explores many of the issues associated with defining 'the population'. Following consultation with data users, it outlines recommended population definitions that could facilitate a more flexible approach. Comparisons are made between the output bases produced from the 2001 Census and the more adaptable outputs potentially available in future if the recommended definitions were used.     

Interim 2001-based national population projections for the United Kingdom and constituent countries

This article describes new 2001-based national population projections which were carried out following the publication in September 2002 of the first results of the 2001 Census. These "interim" projections, carried out by the Government Actuary in consultation with the Registrars General, take preliminary account of the results of the Census which showed that the base population used in previous projections was overestimated. The interim projections also incorporate a reduced assumption of net international migration to the United Kingdom, informed by the first results of the 2001 Census and taking account of more recent migration information. The population of the United Kingdom is now projected to increase from an estimated 58.8 million in 2001 to reach 63.2 million by 2026. The projected population at 2026 is about 1.8 million (2.8 per cent) lower than in the previous (2000-based) projections.     

Fifty years of United Kingdom national population projections: how accurate have they been?

This article considers the accuracy of the official national population projections made for the UK over the last fifty years The findings take account of the revision to population estimates following the 2001 Census and are largely similar to the findings of a previous review carried out after the 1991 Census. The total population has been projected reasonably accurately but this is largely a chance result of compensating errors in the assumptions of fertility, mortality and net migration. The largest differences between projected and actual populations are for the very young and the very old, while projections of the working age population have been comparatively accurate. Fertility and mortality errors have reduced in more recent projections, while migration errors have grown. However, this may simply reflect the volatility or stability of the respective time-series at the time the projections are made. Changes in estimates of the past and current size of the population (highlighted by the revisions made to population estimates following the 2001 Census) are also shown to play a part in explaining projection error.     

Quality assuring the 2011 Census population estimates

The 2011 Census is a once in a decade opportunity to gain an accurate picture of the population. Quality assurance of the census population estimates is vital to ensure data robustness and that users have confidence in the results. This article provides a detailed summary of the methods being used to achieve this quality assurance, including the processes and adjustments.     

Covering all bases: early thoughts for population bases for the 2011 Census

This article discusses early thinking on the options for the population bases to be used in the 2011 Census. It describes some of the work being conducted to enable a decision about bases to be reached, including historic and international reviews of censuses. It also discusses the implications that our rapidly changing society has for census planning.     

Efficiency decomposition with shared inputs and outputs in two-stage DEA

Data envelopment analysis (DEA) is an effective non-parametric method for measuring the relative efficiencies of decision making units (DMUs) with multiple inputs and outputs. In many real situations, the internal structure of DMUs is a two-stage network process with shared inputs used in both stages and common outputs produced by the both stages. For example, hospitals have a two-stage network structure. Stage 1 consumes resources such as information technology system, plant, equipment and admin personnel to generate outputs such as medical records, laundry and housekeeping. Stage 2 consumes the same set of resources used by stage 1 (named shared inputs) and the outputs generated by stage 1 (named intermediate measures) to provide patient services. Besides, some of outputs, for instance, patient satisfaction degrees, are generated by the two individual stages together (named shared outputs). Since some of shared inputs and outputs are hard split up and allocated to each individual stage, it needs to develop two-stage DEA methods for evaluating the performance of two-stage network processes in such problems. This paper extends the centralized model to measure the DEA efficiency of the two-stage process with non splittable shared inputs and outputs. A weighted additive approach is used to combine the two individual stages. Moreover, additive efficiency decomposition models are developed to simultaneously evaluate the maximal and the minimal achievable efficiencies for the individual stages. Finally, an example of 17 city branches of China Construction Bank in Anhui Province is employed to illustrate the proposed approach.     

The 2007 Census Test: a major step towards the 2011 Census

The Office for National Statistics (ONS) is planning a major Census field test in 2007. It will form part of the planning and testing programme leading to up the next Census of Population for England and Wales in 2011, which will also include a Rehearsal in 2009. The 2007 Test will be a large-scale test in five local authority (LA) areas selected to reflect a range of field conditions, covering some 100,000 households in total. Within England the Test will cover parts of Bath and North East Somerset, Camden, Liverpool and Stoke-on-Trent. In Wales the Test will take place in Carmarthenshire. The selected LAs have been chosen to provide a varied cross-section of the population and types of housing that would be covered in a full census. This article sets out the main aims for the Test and describes the design and location of the sampled areas and the basis for their selection. It goes on to detail the ways (previously reported in Population Trend 1251) in which the ONS Census team and the LAs involved are working in partnership in planning the census enumeration with the long-term view of improving overall census coverage and user confidence in the results. The article notes that decisions on the topics to be covered in the 2007 Test have only recently been decided, and concludes with an overview of the qustions to be included in the 2007 Test questionnaire.     

Estimates of the population by ethnic group for areas within England

This article describes, and provides some initial analysis of, the experimental population estimates by ethnic group for areas within England published by the Office for National Statistics (ONS) in January 2006. The article considers growth and the population structure of each of the ethnic groups identified in the 2001 Census; subnational patterns of change; population turnover; and measures of diversity and segregation, and also provides a comparison of the estimates and corresponding sample-based estimates from the Labour Force Survey.     

Opportunities for new research using the post-2001 ONS Longitudinal Study

The addition of 2001 Census data to the ONS Longitudinal Study extends the range of research topics that this unique data resource can support. Census questions on religion, care-giving and self-rated health that were asked for the first time in 2001 and the repetition of 1991 questions on limiting long-standing illness and ethnicity raise opportunities for new longitudinal investigation in these areas. This article describes how new 2001 methodologies including data imputation, the One Number Census and de jure enumeration affect the LS database. The support service for existing and prospective LS users is described.     

No vote--no census: an account of some of the events of 1910-1911

The 2011 Census on the 27 March will be the latest in a series spanning over two centuries and covering vast demographic changes in the British population. Although the underlying aim of each census since 1801 has been to obtain an accurate enumeration of the population, successive censuses have adapted to changing social and technological circumstances, asking appropriate questions and using the best available technology to compile results. A century ago, the 1911 Census represented a shift from earlier censuses in its use of machine tabulation. Despite this innovation, however, what is perhaps most interesting about 1911 is the social and political circumstances: the 1911 Census took place against the background of a threatened boycott by the suffragette movement. The article demonstrates how, though times change and technology moves on, a successful census was conducted despite the deeply sensitive political times.     

Families, groups and clusters of local and health authorities: revised for authorities in 1999

This is the second of two articles describing the revision of The ONS classification of local and health authorities of Great Britain to take account of area changes in the 1990's. It presents local authorities in Great Britain as at April 1999 in terms of Families, Groups and Clusters, based on 37 socio-economic and demographic variables from the 1991 Census. Health authorities are presented in terms of Families and Groups only, based on the same variables. The previous article (in Population Trends 98) presented, for each local and health authority, up to four other authorities to which it is 'most similar'.     

The Census Coverage Survey--the key element of a one number census

The key measure of census quality is the level of response achieved. In recent censuses worldwide this level has been in the high nineties per cent. This was also true of censuses in Britain in 1991 (98 per cent). However, what was particularly noticeable about the census in Britain in 1991 was the differential response rate and the difficulty in effectively measuring this. The One Number Census programme was set up in the UK to research and develop a more effective methodology to measure and account for underenumeration in the 2001 Census. The key element in this process is the Census Coverage Survey--a significantly larger and redesigned post-enumeration survey. This article describes the planning and design of the survey with particular emphasis on the implementation of the proposed field methodology in practice. It also provides a high-level overview of the success of the survey.